mlsanityData to 14 Oct 2026

Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

arXiv 1605.02065 ↗First posted 6 May 2016cs.CR cs.DS cs.ITcited by 346

Not on the map. Why?

Abstract (arXiv)

"Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Renyi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and raise a few new questions. We also unify this approach with approximate differential privacy by giving an appropriate definition of "approximate concentrated differential privacy."

Key facts. Cited by 346 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 52; 2022: 60; 2023: 69; 2024: 62; 2025: 50; 2026: 53.

346 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  2. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  3. 2021Numerical Composition of Differential Privacycited by 180
  4. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 153
  5. 2022Reconstructing Training Data with Informed Adversariescited by 148
  6. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  7. 2023Privacy Auditing with One (1) Training Runcited by 123
  8. 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
  9. 2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
  10. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 86
  11. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 85
  12. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
38 more
  1. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
  2. 2023Federated Learning of Gboard Language Models with Differential Privacycited by 66
  3. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 59
  4. 2022Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streamscited by 59
  5. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 57
  6. 2021Differentially Private Query Release Through Adaptive Projectioncited by 52
  7. 2022Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributionscited by 52
  8. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 52
  9. 2023Privacy-Preserving In-Context Learning for Large Language Modelscited by 50
  10. 2023(Amplified) Banded Matrix Factorization: A unified approach to private trainingcited by 49
  11. 2022Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learningcited by 48
  12. 2021Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Datacited by 47
  13. 2021Covariance-Aware Private Mean Estimation Without Private Covariance Estimationcited by 46
  14. 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 45
  15. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  16. 2021Tighter expected generalization error bounds via Wasserstein distancecited by 43
  17. 2021Leveraging Public Data for Practical Private Query Releasecited by 39
  18. 2021Private and polynomial time algorithms for learning Gaussians and beyondcited by 39
  19. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  20. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  21. 2022Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimizationcited by 36
  22. 2022Private Synthetic Data for Multitask Learning and Marginal Queriescited by 35
  23. 2021FriendlyCore: Practical Differentially Private Aggregationcited by 34
  24. 2021A Private and Computationally-Efficient Estimator for Unbounded Gaussianscited by 34
  25. 2022SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compressioncited by 34
  26. 2023Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Modelcited by 33
  27. 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
  28. 2021Federated f-Differential Privacycited by 29
  29. 2022Stronger Privacy Amplification by Shuffling for R'enyi and Approximate Differential Privacycited by 29
  30. 2021Lossless Compression of Efficient Private Local Randomizerscited by 27
  31. 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
  32. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  33. 2022Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimationcited by 25
  34. 2023Differentially Private Attention Computationcited by 25
  35. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  36. 2024Private prediction for large-scale synthetic text generationcited by 24
  37. 2021Differentially Private Quantilescited by 23
  38. 2022Learning to Generate Image Embeddings with User-level Differential Privacycited by 23

50 most cited of 346 All 346 (JSON)